paper-with-me

홈 › Papers

End-to-end Person Search Sequentially Trained on Aggregated Dataset

2022-01-24 · Angelique Loesch, Jaonary Rabarisoa, Romaric Audigier

In video surveillance applications, person search is a challenging task consisting in detecting people and extracting features from their silhouette for re-identification (re-ID) purpose. We propose a new end-to-end model that jointly computes detection and feature extraction steps through a single deep Convolutional Neural Network architecture. Sharing feature maps between the two tasks for jointly describing people commonalities and specificities allows faster runtime, which is valuable in real-world applications. In addition to reaching state-of-the-art accuracy, this multi-task model can be sequentially trained task-by-task, which results in a broader acceptance of input dataset types. Indeed, we show that aggregating more pedestrian detection datasets without costly identity annotations makes the shared feature maps more generic, and improves re-ID precision. Moreover, these boosted shared feature maps result in re-ID features more robust to a cross-dataset scenario.

📄 PDF Abstract BibTeX arXiv:2201.09604

Code (0)

등록된 구현이 없습니다.

Tasks

Pedestrian DetectionPerson Search

Similar Papers 제목 키워드 기반

Sequentially Aggregated Convolutional Networks

2018-11-27 · Yiwen Huang, Rihui Wu, Pinglai Ou, Ziyong Feng

Modern deep networks generally implement a certain form of shortcut connections to alleviate optimization difficulties. However, we observe that such network topology alters the nature of deep networks. In many ways, the…

General Classificationimage-classificationImage Classification

FedAH: Aggregated Head for Personalized Federated Learning

2024-12-02 · Pengzhan Zhou, Yuepeng He, Yijun Zhai, Kaixin Gao 외

Recently, Federated Learning (FL) has gained popularity for its privacy-preserving and collaborative learning capabilities. Personalized Federated Learning (PFL), building upon FL, aims to address the issue of statistica…

Federated LearningPersonalized Federated LearningPrivacy Preserving

Churn-Aware Recommendation Planning under Aggregated Preference Feedback

2025-07-06 · Gur Keinan, Omer Ben-Porat arxiv

We study a sequential decision-making problem motivated by recent regulatory and technological shifts that limit access to individual user data in recommender systems (RSs), leaving only population-level preference infor…

DesignPref: Capturing Personal Preferences in Visual Design Generation

2025-11-25 · Yi-Hao Peng, Jeffrey P. Bigham, Jason Wu arxiv

Generative models, such as large language models and text-to-image diffusion models, are increasingly used to create visual designs like user interfaces (UIs) and presentation slides. Finetuning and benchmarking these ge…

Active Learning for Regression with Aggregated Outputs

2022-10-04 · Tomoharu Iwata

Due to the privacy protection or the difficulty of data collection, we cannot observe individual outputs for each instance, but we can observe aggregated outputs that are summed over multiple instances in a set in some r…

Active LearningGaussian Processesregression